Multi-scale target detection model method based on metric learning

A technique of metric learning and target detection, applied in neural learning methods, biological neural network models, character and pattern recognition, etc.

Active Publication Date: 2020-09-11
BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
View PDF4 Cites 22 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For the existing RepMet network model, solve the following two problems: (1) How to perform the regression frame regression of the region of interest in the image when using a small num...

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Multi-scale target detection model method based on metric learning
  • Multi-scale target detection model method based on metric learning
  • Multi-scale target detection model method based on metric learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0084] Below in conjunction with accompanying drawing, further describe the present invention through embodiment, but do not limit the scope of the present invention in any way.

[0085] Method flow chart as figure 1 As shown, the model structure is as figure 2 shown. The method of the present invention includes: 1) building a multi-scale target detection model based on metric learning: the model adopts a two-step detection strategy to realize the detection and recognition of the target, a region of interest extraction module, and a target classification and recognition module; 2) pre-training multiple Scale model: Train the border regression prediction of the multi-scale model part of the model on a large-scale data set, and then transfer learning to this model for fine-tuning to extract the region of interest in the image; 3) Metric learning target detection: use The fully connected layer learns the convolution features, and identifies the region of interest by measuring ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a multi-scale target detection model method based on metric learning, and the method comprises the steps: carrying out the initialization of a network through employing a pre-trained model through employing the idea of transfer learning, adding a loss function to carry out the fine adjustment of a weight parameter of the network, and improving the regression precision of aregion of interest in an image; adding a full-connection layer to vectorize feature information after a feature map is extracted from a region of interest in an image, and then performing distance measurement by using the feature information extracted by the full-connection layer to realize classification and identification of target region information. By adopting the method of the invention, theloss of the feature information can be reduced, and the classification and recognition accuracy of the detection target is improved.

Description

technical field [0001] The invention relates to image processing and small-sample target detection technology, in particular to a multi-scale target detection model method based on metric learning, which belongs to the technical fields of computer vision and edge computing. Background technique [0002] In recent years, deep learning has achieved great success in image classification and detection tasks. Because of its superior performance in image feature extraction, it can learn the feature information required for tasks from data and is widely used in Various areas of research in computer vision. For the existing deep neural network, due to its complex network structure with a large number of parameters, a large amount of data is required for training to complete specific computer vision tasks. However, in some practical applications, it is very difficult to collect a large amount of data, so how to use the existing small amount of data to achieve specific computer visio...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
IPC IPC(8): G06K9/32G06K9/62G06T7/00G06N3/04G06N3/08
CPCG06T7/0002G06N3/08G06T2207/20104G06T2207/20081G06T2207/20076G06V10/25G06N3/045G06F18/241G06F18/214Y02T10/40
Inventor 于重重萨良兵马先钦陈秀新赵霞
Owner BEIJING TECHNOLOGY AND BUSINESS UNIVERSITY
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap